crawlo 1.1.1__py3-none-any.whl → 1.1.3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (128) hide show
  1. crawlo/__init__.py +34 -33
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +40 -40
  4. crawlo/commands/__init__.py +13 -13
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +152 -126
  7. crawlo/commands/list.py +156 -147
  8. crawlo/commands/run.py +285 -285
  9. crawlo/commands/startproject.py +196 -111
  10. crawlo/commands/stats.py +188 -188
  11. crawlo/commands/utils.py +187 -0
  12. crawlo/config.py +280 -0
  13. crawlo/core/__init__.py +2 -2
  14. crawlo/core/engine.py +171 -158
  15. crawlo/core/enhanced_engine.py +190 -0
  16. crawlo/core/processor.py +40 -40
  17. crawlo/core/scheduler.py +166 -57
  18. crawlo/crawler.py +1028 -495
  19. crawlo/downloader/__init__.py +242 -78
  20. crawlo/downloader/aiohttp_downloader.py +212 -199
  21. crawlo/downloader/cffi_downloader.py +251 -241
  22. crawlo/downloader/httpx_downloader.py +259 -246
  23. crawlo/event.py +11 -11
  24. crawlo/exceptions.py +82 -78
  25. crawlo/extension/__init__.py +31 -31
  26. crawlo/extension/log_interval.py +49 -49
  27. crawlo/extension/log_stats.py +44 -44
  28. crawlo/extension/logging_extension.py +34 -34
  29. crawlo/filters/__init__.py +154 -37
  30. crawlo/filters/aioredis_filter.py +242 -150
  31. crawlo/filters/memory_filter.py +269 -202
  32. crawlo/items/__init__.py +23 -23
  33. crawlo/items/base.py +21 -21
  34. crawlo/items/fields.py +53 -53
  35. crawlo/items/items.py +104 -104
  36. crawlo/middleware/__init__.py +21 -21
  37. crawlo/middleware/default_header.py +32 -32
  38. crawlo/middleware/download_delay.py +28 -28
  39. crawlo/middleware/middleware_manager.py +135 -135
  40. crawlo/middleware/proxy.py +248 -245
  41. crawlo/middleware/request_ignore.py +30 -30
  42. crawlo/middleware/response_code.py +18 -18
  43. crawlo/middleware/response_filter.py +26 -26
  44. crawlo/middleware/retry.py +125 -90
  45. crawlo/mode_manager.py +201 -0
  46. crawlo/network/__init__.py +21 -7
  47. crawlo/network/request.py +311 -203
  48. crawlo/network/response.py +271 -166
  49. crawlo/pipelines/__init__.py +22 -13
  50. crawlo/pipelines/bloom_dedup_pipeline.py +157 -0
  51. crawlo/pipelines/console_pipeline.py +39 -39
  52. crawlo/pipelines/csv_pipeline.py +317 -0
  53. crawlo/pipelines/database_dedup_pipeline.py +225 -0
  54. crawlo/pipelines/json_pipeline.py +219 -0
  55. crawlo/pipelines/memory_dedup_pipeline.py +116 -0
  56. crawlo/pipelines/mongo_pipeline.py +116 -116
  57. crawlo/pipelines/mysql_pipeline.py +195 -195
  58. crawlo/pipelines/pipeline_manager.py +56 -56
  59. crawlo/pipelines/redis_dedup_pipeline.py +163 -0
  60. crawlo/project.py +153 -153
  61. crawlo/queue/__init__.py +0 -0
  62. crawlo/queue/pqueue.py +37 -0
  63. crawlo/queue/queue_manager.py +308 -0
  64. crawlo/queue/redis_priority_queue.py +209 -0
  65. crawlo/settings/__init__.py +7 -7
  66. crawlo/settings/default_settings.py +245 -167
  67. crawlo/settings/setting_manager.py +99 -99
  68. crawlo/spider/__init__.py +639 -129
  69. crawlo/stats_collector.py +59 -59
  70. crawlo/subscriber.py +106 -106
  71. crawlo/task_manager.py +30 -27
  72. crawlo/templates/crawlo.cfg.tmpl +10 -10
  73. crawlo/templates/project/__init__.py.tmpl +3 -3
  74. crawlo/templates/project/items.py.tmpl +17 -17
  75. crawlo/templates/project/middlewares.py.tmpl +87 -76
  76. crawlo/templates/project/pipelines.py.tmpl +342 -64
  77. crawlo/templates/project/run.py.tmpl +252 -0
  78. crawlo/templates/project/settings.py.tmpl +251 -54
  79. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  80. crawlo/templates/spider/spider.py.tmpl +178 -32
  81. crawlo/utils/__init__.py +7 -7
  82. crawlo/utils/controlled_spider_mixin.py +440 -0
  83. crawlo/utils/date_tools.py +233 -233
  84. crawlo/utils/db_helper.py +343 -343
  85. crawlo/utils/func_tools.py +82 -82
  86. crawlo/utils/large_scale_config.py +287 -0
  87. crawlo/utils/large_scale_helper.py +344 -0
  88. crawlo/utils/log.py +128 -128
  89. crawlo/utils/queue_helper.py +176 -0
  90. crawlo/utils/request.py +267 -267
  91. crawlo/utils/request_serializer.py +220 -0
  92. crawlo/utils/spider_loader.py +62 -62
  93. crawlo/utils/system.py +11 -11
  94. crawlo/utils/tools.py +4 -4
  95. crawlo/utils/url.py +39 -39
  96. crawlo-1.1.3.dist-info/METADATA +635 -0
  97. crawlo-1.1.3.dist-info/RECORD +113 -0
  98. examples/__init__.py +7 -7
  99. examples/controlled_spider_example.py +205 -0
  100. tests/__init__.py +7 -7
  101. tests/test_final_validation.py +154 -0
  102. tests/test_proxy_health_check.py +32 -32
  103. tests/test_proxy_middleware_integration.py +136 -136
  104. tests/test_proxy_providers.py +56 -56
  105. tests/test_proxy_stats.py +19 -19
  106. tests/test_proxy_strategies.py +59 -59
  107. tests/test_redis_config.py +29 -0
  108. tests/test_redis_queue.py +225 -0
  109. tests/test_request_serialization.py +71 -0
  110. tests/test_scheduler.py +242 -0
  111. crawlo/pipelines/mysql_batch_pipline.py +0 -273
  112. crawlo/utils/pqueue.py +0 -174
  113. crawlo-1.1.1.dist-info/METADATA +0 -220
  114. crawlo-1.1.1.dist-info/RECORD +0 -100
  115. examples/baidu_spider/__init__.py +0 -7
  116. examples/baidu_spider/demo.py +0 -94
  117. examples/baidu_spider/items.py +0 -46
  118. examples/baidu_spider/middleware.py +0 -49
  119. examples/baidu_spider/pipeline.py +0 -55
  120. examples/baidu_spider/run.py +0 -27
  121. examples/baidu_spider/settings.py +0 -121
  122. examples/baidu_spider/spiders/__init__.py +0 -7
  123. examples/baidu_spider/spiders/bai_du.py +0 -61
  124. examples/baidu_spider/spiders/miit.py +0 -159
  125. examples/baidu_spider/spiders/sina.py +0 -79
  126. {crawlo-1.1.1.dist-info → crawlo-1.1.3.dist-info}/WHEEL +0 -0
  127. {crawlo-1.1.1.dist-info → crawlo-1.1.3.dist-info}/entry_points.txt +0 -0
  128. {crawlo-1.1.1.dist-info → crawlo-1.1.3.dist-info}/top_level.txt +0 -0
crawlo/commands/run.py CHANGED
@@ -1,286 +1,286 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- # @Time : 2025-08-31 22:36
5
- # @Author : crawl-coder
6
- # @Desc : 命令行入口:crawlo run <spider_name>|all,用于运行指定爬虫。
7
- """
8
- import sys
9
- import asyncio
10
- import configparser
11
- from pathlib import Path
12
- from importlib import import_module
13
-
14
- from rich.console import Console
15
- from rich.panel import Panel
16
- from rich.table import Table
17
- from rich.text import Text
18
- from rich import box
19
- from rich.progress import Progress, SpinnerColumn, TextColumn
20
-
21
- from crawlo.crawler import CrawlerProcess
22
- from crawlo.utils.log import get_logger
23
- from crawlo.project import get_settings
24
- from crawlo.commands.stats import record_stats
25
-
26
- logger = get_logger(__name__)
27
- console = Console()
28
-
29
-
30
- def get_project_root():
31
- """
32
- 向上查找 crawlo.cfg 来确定项目根目录
33
- """
34
- current = Path.cwd()
35
- for _ in range(10):
36
- cfg = current / "crawlo.cfg"
37
- if cfg.exists():
38
- return current
39
- if current == current.parent:
40
- break
41
- current = current.parent
42
- return None
43
-
44
-
45
- def main(args):
46
- """
47
- 主函数:运行指定爬虫
48
- 用法:
49
- crawlo run <spider_name>|all [--json] [--no-stats]
50
- """
51
- if len(args) < 1:
52
- console.print("[bold red]❌ Usage:[/bold red] [blue]crawlo run[/blue] <spider_name>|all [bold yellow][--json] [--no-stats][/bold yellow]")
53
- console.print("💡 Examples:")
54
- console.print(" [blue]crawlo run baidu[/blue]")
55
- console.print(" [blue]crawlo run all[/blue]")
56
- console.print(" [blue]crawlo run all --json --no-stats[/blue]")
57
- return 1
58
-
59
- # 解析参数
60
- spider_arg = args[0]
61
- show_json = "--json" in args
62
- no_stats = "--no-stats" in args
63
-
64
- try:
65
- # 1. 查找项目根目录
66
- project_root = get_project_root()
67
- if not project_root:
68
- msg = ":cross_mark: [bold red]Cannot find 'crawlo.cfg'[/bold red]\n💡 Run this command inside your project directory."
69
- if show_json:
70
- console.print_json(data={"success": False, "error": "Project root not found"})
71
- return 1
72
- else:
73
- console.print(Panel(
74
- Text.from_markup(msg),
75
- title="❌ Not in a Crawlo Project",
76
- border_style="red",
77
- padding=(1, 2)
78
- ))
79
- return 1
80
-
81
- project_root_str = str(project_root)
82
- if project_root_str not in sys.path:
83
- sys.path.insert(0, project_root_str)
84
-
85
- # 2. 读取 crawlo.cfg 获取 settings 模块
86
- cfg_file = project_root / "crawlo.cfg"
87
- if not cfg_file.exists():
88
- msg = f"crawlo.cfg not found in {project_root}"
89
- if show_json:
90
- console.print_json(data={"success": False, "error": msg})
91
- return 1
92
- else:
93
- console.print(Panel(msg, title="❌ Missing Config", border_style="red"))
94
- return 1
95
-
96
- config = configparser.ConfigParser()
97
- config.read(cfg_file, encoding="utf-8")
98
-
99
- if not config.has_section("settings") or not config.has_option("settings", "default"):
100
- msg = "Missing [settings] section or 'default' option in crawlo.cfg"
101
- if show_json:
102
- console.print_json(data={"success": False, "error": msg})
103
- return 1
104
- else:
105
- console.print(Panel(msg, title="❌ Invalid Config", border_style="red"))
106
- return 1
107
-
108
- settings_module = config.get("settings", "default")
109
- project_package = settings_module.split(".")[0]
110
-
111
- # 3. 确保项目包可导入
112
- try:
113
- import_module(project_package)
114
- except ImportError as e:
115
- msg = f"Failed to import project package '{project_package}': {e}"
116
- if show_json:
117
- console.print_json(data={"success": False, "error": msg})
118
- return 1
119
- else:
120
- console.print(Panel(msg, title="❌ Import Error", border_style="red"))
121
- return 1
122
-
123
- # 4. 加载 settings 和爬虫模块
124
- settings = get_settings()
125
- spider_modules = [f"{project_package}.spiders"]
126
- process = CrawlerProcess(settings=settings, spider_modules=spider_modules)
127
-
128
- # === 情况1:运行所有爬虫 ===
129
- if spider_arg.lower() == "all":
130
- spider_names = process.get_spider_names()
131
- if not spider_names:
132
- msg = "No spiders found."
133
- if show_json:
134
- console.print_json(data={"success": False, "error": msg})
135
- return 1
136
- else:
137
- console.print(Panel(
138
- Text.from_markup(
139
- ":cross_mark: [bold red]No spiders found.[/bold red]\n\n"
140
- "[bold]💡 Make sure:[/bold]\n"
141
- " • Spiders are defined in '[cyan]spiders/[/cyan]'\n"
142
- " • They have a [green]`name`[/green] attribute\n"
143
- " • Modules are imported (e.g. via [cyan]__init__.py[/cyan])"
144
- ),
145
- title="❌ No Spiders",
146
- border_style="red",
147
- padding=(1, 2)
148
- ))
149
- return 1
150
-
151
- # 显示即将运行的爬虫列表
152
- table = Table(
153
- title=f"🚀 Starting ALL {len(spider_names)} spider(s)",
154
- box=box.ROUNDED,
155
- show_header=True,
156
- header_style="bold magenta"
157
- )
158
- table.add_column("Name", style="cyan")
159
- table.add_column("Class", style="green")
160
-
161
- for name in sorted(spider_names):
162
- cls = process.get_spider_class(name)
163
- table.add_row(name, cls.__name__)
164
-
165
- console.print(table)
166
- console.print()
167
-
168
- # 注册 stats 记录(除非 --no-stats)
169
- if not no_stats:
170
- for crawler in process.crawlers:
171
- crawler.signals.connect(record_stats, signal="spider_closed")
172
-
173
- # 并行运行所有爬虫
174
- with Progress(
175
- SpinnerColumn(),
176
- TextColumn("[progress.description]{task.description}"),
177
- transient=True,
178
- ) as progress:
179
- task = progress.add_task("Running all spiders...", total=None)
180
- asyncio.run(process.crawl(spider_names))
181
-
182
- if show_json:
183
- console.print_json(data={"success": True, "spiders": spider_names})
184
- else:
185
- console.print(Panel(
186
- ":tada: [bold green]All spiders completed successfully![/bold green]",
187
- title="✅ All Done",
188
- border_style="green"
189
- ))
190
- return 0
191
-
192
- # === 情况2:运行单个爬虫 ===
193
- spider_name = spider_arg
194
- if not process.is_spider_registered(spider_name):
195
- available = process.get_spider_names()
196
- msg = f"Spider '[cyan]{spider_name}[/cyan]' not found."
197
- if show_json:
198
- console.print_json(data={
199
- "success": False,
200
- "error": msg,
201
- "available": available
202
- })
203
- return 1
204
- else:
205
- panel_content = Text.from_markup(msg + "\n")
206
- if available:
207
- panel_content.append("\n💡 Available spiders:\n")
208
- for name in sorted(available):
209
- cls = process.get_spider_class(name)
210
- panel_content.append(f" • [cyan]{name}[/cyan] ([green]{cls.__name__}[/green])\n")
211
- else:
212
- panel_content.append("\n💡 No spiders found. Check your spiders module.")
213
-
214
- console.print(Panel(
215
- panel_content,
216
- title="❌ Spider Not Found",
217
- border_style="red",
218
- padding=(1, 2)
219
- ))
220
- return 1
221
-
222
- spider_class = process.get_spider_class(spider_name)
223
-
224
- # 显示启动信息
225
- if not show_json:
226
- info_table = Table(
227
- title=f"🚀 Starting Spider: [bold cyan]{spider_name}[/bold cyan]",
228
- box=box.SIMPLE,
229
- show_header=False,
230
- title_style="bold green"
231
- )
232
- info_table.add_column("Key", style="yellow")
233
- info_table.add_column("Value", style="cyan")
234
- info_table.add_row("Project", project_package)
235
- info_table.add_row("Class", spider_class.__name__)
236
- info_table.add_row("Module", spider_class.__module__)
237
- console.print(info_table)
238
- console.print()
239
-
240
- # 注册 stats 记录
241
- if not no_stats:
242
- for crawler in process.crawlers:
243
- crawler.signals.connect(record_stats, signal="spider_closed")
244
-
245
- # 运行爬虫
246
- with Progress(
247
- SpinnerColumn(),
248
- TextColumn("[progress.description]{task.description}"),
249
- transient=True,
250
- ) as progress:
251
- task = progress.add_task(f"Running {spider_name}...", total=None)
252
- asyncio.run(process.crawl(spider_name))
253
-
254
- if show_json:
255
- console.print_json(data={"success": True, "spider": spider_name})
256
- else:
257
- console.print(Panel(
258
- f":tada: [bold green]Spider '[cyan]{spider_name}[/cyan]' completed successfully![/bold green]",
259
- title="✅ Done",
260
- border_style="green"
261
- ))
262
- return 0
263
-
264
- except KeyboardInterrupt:
265
- msg = "⚠️ Spider interrupted by user."
266
- if show_json:
267
- console.print_json(data={"success": False, "error": msg})
268
- else:
269
- console.print(f"[bold yellow]{msg}[/bold yellow]")
270
- return 1
271
- except Exception as e:
272
- logger.exception("Exception during 'crawlo run'")
273
- msg = f"Unexpected error: {e}"
274
- if show_json:
275
- console.print_json(data={"success": False, "error": msg})
276
- else:
277
- console.print(f"[bold red]❌ {msg}[/bold red]")
278
- return 1
279
-
280
-
281
- if __name__ == "__main__":
282
- """
283
- 支持直接运行:
284
- python -m crawlo.commands.run spider_name
285
- """
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ # @Time : 2025-08-31 22:36
5
+ # @Author : crawl-coder
6
+ # @Desc : 命令行入口:crawlo run <spider_name>|all,用于运行指定爬虫。
7
+ """
8
+ import sys
9
+ import asyncio
10
+ import configparser
11
+ from pathlib import Path
12
+ from importlib import import_module
13
+
14
+ from rich.console import Console
15
+ from rich.panel import Panel
16
+ from rich.table import Table
17
+ from rich.text import Text
18
+ from rich import box
19
+ from rich.progress import Progress, SpinnerColumn, TextColumn
20
+
21
+ from crawlo.crawler import CrawlerProcess
22
+ from crawlo.utils.log import get_logger
23
+ from crawlo.project import get_settings
24
+ from crawlo.commands.stats import record_stats
25
+
26
+ logger = get_logger(__name__)
27
+ console = Console()
28
+
29
+
30
+ def get_project_root():
31
+ """
32
+ 向上查找 crawlo.cfg 来确定项目根目录
33
+ """
34
+ current = Path.cwd()
35
+ for _ in range(10):
36
+ cfg = current / "crawlo.cfg"
37
+ if cfg.exists():
38
+ return current
39
+ if current == current.parent:
40
+ break
41
+ current = current.parent
42
+ return None
43
+
44
+
45
+ def main(args):
46
+ """
47
+ 主函数:运行指定爬虫
48
+ 用法:
49
+ crawlo run <spider_name>|all [--json] [--no-stats]
50
+ """
51
+ if len(args) < 1:
52
+ console.print("[bold red]❌ Usage:[/bold red] [blue]crawlo run[/blue] <spider_name>|all [bold yellow][--json] [--no-stats][/bold yellow]")
53
+ console.print("💡 Examples:")
54
+ console.print(" [blue]crawlo run baidu[/blue]")
55
+ console.print(" [blue]crawlo run all[/blue]")
56
+ console.print(" [blue]crawlo run all --json --no-stats[/blue]")
57
+ return 1
58
+
59
+ # 解析参数
60
+ spider_arg = args[0]
61
+ show_json = "--json" in args
62
+ no_stats = "--no-stats" in args
63
+
64
+ try:
65
+ # 1. 查找项目根目录
66
+ project_root = get_project_root()
67
+ if not project_root:
68
+ msg = ":cross_mark: [bold red]Cannot find 'crawlo.cfg'[/bold red]\n💡 Run this command inside your project directory."
69
+ if show_json:
70
+ console.print_json(data={"success": False, "error": "Project root not found"})
71
+ return 1
72
+ else:
73
+ console.print(Panel(
74
+ Text.from_markup(msg),
75
+ title="❌ Not in a Crawlo Project",
76
+ border_style="red",
77
+ padding=(1, 2)
78
+ ))
79
+ return 1
80
+
81
+ project_root_str = str(project_root)
82
+ if project_root_str not in sys.path:
83
+ sys.path.insert(0, project_root_str)
84
+
85
+ # 2. 读取 crawlo.cfg 获取 settings 模块
86
+ cfg_file = project_root / "crawlo.cfg"
87
+ if not cfg_file.exists():
88
+ msg = f"crawlo.cfg not found in {project_root}"
89
+ if show_json:
90
+ console.print_json(data={"success": False, "error": msg})
91
+ return 1
92
+ else:
93
+ console.print(Panel(msg, title="❌ Missing Config", border_style="red"))
94
+ return 1
95
+
96
+ config = configparser.ConfigParser()
97
+ config.read(cfg_file, encoding="utf-8")
98
+
99
+ if not config.has_section("settings") or not config.has_option("settings", "default"):
100
+ msg = "Missing [settings] section or 'default' option in crawlo.cfg"
101
+ if show_json:
102
+ console.print_json(data={"success": False, "error": msg})
103
+ return 1
104
+ else:
105
+ console.print(Panel(msg, title="❌ Invalid Config", border_style="red"))
106
+ return 1
107
+
108
+ settings_module = config.get("settings", "default")
109
+ project_package = settings_module.split(".")[0]
110
+
111
+ # 3. 确保项目包可导入
112
+ try:
113
+ import_module(project_package)
114
+ except ImportError as e:
115
+ msg = f"Failed to import project package '{project_package}': {e}"
116
+ if show_json:
117
+ console.print_json(data={"success": False, "error": msg})
118
+ return 1
119
+ else:
120
+ console.print(Panel(msg, title="❌ Import Error", border_style="red"))
121
+ return 1
122
+
123
+ # 4. 加载 settings 和爬虫模块
124
+ settings = get_settings()
125
+ spider_modules = [f"{project_package}.spiders"]
126
+ process = CrawlerProcess(settings=settings, spider_modules=spider_modules)
127
+
128
+ # === 情况1:运行所有爬虫 ===
129
+ if spider_arg.lower() == "all":
130
+ spider_names = process.get_spider_names()
131
+ if not spider_names:
132
+ msg = "No spiders found."
133
+ if show_json:
134
+ console.print_json(data={"success": False, "error": msg})
135
+ return 1
136
+ else:
137
+ console.print(Panel(
138
+ Text.from_markup(
139
+ ":cross_mark: [bold red]No spiders found.[/bold red]\n\n"
140
+ "[bold]💡 Make sure:[/bold]\n"
141
+ " • Spiders are defined in '[cyan]spiders/[/cyan]'\n"
142
+ " • They have a [green]`name`[/green] attribute\n"
143
+ " • Modules are imported (e.g. via [cyan]__init__.py[/cyan])"
144
+ ),
145
+ title="❌ No Spiders",
146
+ border_style="red",
147
+ padding=(1, 2)
148
+ ))
149
+ return 1
150
+
151
+ # 显示即将运行的爬虫列表
152
+ table = Table(
153
+ title=f"🚀 Starting ALL {len(spider_names)} spider(s)",
154
+ box=box.ROUNDED,
155
+ show_header=True,
156
+ header_style="bold magenta"
157
+ )
158
+ table.add_column("Name", style="cyan")
159
+ table.add_column("Class", style="green")
160
+
161
+ for name in sorted(spider_names):
162
+ cls = process.get_spider_class(name)
163
+ table.add_row(name, cls.__name__)
164
+
165
+ console.print(table)
166
+ console.print()
167
+
168
+ # 注册 stats 记录(除非 --no-stats)
169
+ if not no_stats:
170
+ for crawler in process.crawlers:
171
+ crawler.signals.connect(record_stats, signal="spider_closed")
172
+
173
+ # 并行运行所有爬虫
174
+ with Progress(
175
+ SpinnerColumn(),
176
+ TextColumn("[progress.description]{task.description}"),
177
+ transient=True,
178
+ ) as progress:
179
+ task = progress.add_task("Running all spiders...", total=None)
180
+ asyncio.run(process.crawl(spider_names))
181
+
182
+ if show_json:
183
+ console.print_json(data={"success": True, "spiders": spider_names})
184
+ else:
185
+ console.print(Panel(
186
+ ":tada: [bold green]All spiders completed successfully![/bold green]",
187
+ title="✅ All Done",
188
+ border_style="green"
189
+ ))
190
+ return 0
191
+
192
+ # === 情况2:运行单个爬虫 ===
193
+ spider_name = spider_arg
194
+ if not process.is_spider_registered(spider_name):
195
+ available = process.get_spider_names()
196
+ msg = f"Spider '[cyan]{spider_name}[/cyan]' not found."
197
+ if show_json:
198
+ console.print_json(data={
199
+ "success": False,
200
+ "error": msg,
201
+ "available": available
202
+ })
203
+ return 1
204
+ else:
205
+ panel_content = Text.from_markup(msg + "\n")
206
+ if available:
207
+ panel_content.append("\n💡 Available spiders:\n")
208
+ for name in sorted(available):
209
+ cls = process.get_spider_class(name)
210
+ panel_content.append(f" • [cyan]{name}[/cyan] ([green]{cls.__name__}[/green])\n")
211
+ else:
212
+ panel_content.append("\n💡 No spiders found. Check your spiders module.")
213
+
214
+ console.print(Panel(
215
+ panel_content,
216
+ title="❌ Spider Not Found",
217
+ border_style="red",
218
+ padding=(1, 2)
219
+ ))
220
+ return 1
221
+
222
+ spider_class = process.get_spider_class(spider_name)
223
+
224
+ # 显示启动信息
225
+ if not show_json:
226
+ info_table = Table(
227
+ title=f"🚀 Starting Spider: [bold cyan]{spider_name}[/bold cyan]",
228
+ box=box.SIMPLE,
229
+ show_header=False,
230
+ title_style="bold green"
231
+ )
232
+ info_table.add_column("Key", style="yellow")
233
+ info_table.add_column("Value", style="cyan")
234
+ info_table.add_row("Project", project_package)
235
+ info_table.add_row("Class", spider_class.__name__)
236
+ info_table.add_row("Module", spider_class.__module__)
237
+ console.print(info_table)
238
+ console.print()
239
+
240
+ # 注册 stats 记录
241
+ if not no_stats:
242
+ for crawler in process.crawlers:
243
+ crawler.signals.connect(record_stats, signal="spider_closed")
244
+
245
+ # 运行爬虫
246
+ with Progress(
247
+ SpinnerColumn(),
248
+ TextColumn("[progress.description]{task.description}"),
249
+ transient=True,
250
+ ) as progress:
251
+ task = progress.add_task(f"Running {spider_name}...", total=None)
252
+ asyncio.run(process.crawl(spider_name))
253
+
254
+ if show_json:
255
+ console.print_json(data={"success": True, "spider": spider_name})
256
+ else:
257
+ console.print(Panel(
258
+ f":tada: [bold green]Spider '[cyan]{spider_name}[/cyan]' completed successfully![/bold green]",
259
+ title="✅ Done",
260
+ border_style="green"
261
+ ))
262
+ return 0
263
+
264
+ except KeyboardInterrupt:
265
+ msg = "⚠️ Spider interrupted by user."
266
+ if show_json:
267
+ console.print_json(data={"success": False, "error": msg})
268
+ else:
269
+ console.print(f"[bold yellow]{msg}[/bold yellow]")
270
+ return 1
271
+ except Exception as e:
272
+ logger.exception("Exception during 'crawlo run'")
273
+ msg = f"Unexpected error: {e}"
274
+ if show_json:
275
+ console.print_json(data={"success": False, "error": msg})
276
+ else:
277
+ console.print(f"[bold red]❌ {msg}[/bold red]")
278
+ return 1
279
+
280
+
281
+ if __name__ == "__main__":
282
+ """
283
+ 支持直接运行:
284
+ python -m crawlo.commands.run spider_name
285
+ """
286
286
  sys.exit(main(sys.argv[1:]))